CN120177465A

CN120177465A - A wearable/adhesive ammonia colorimetric sensor, preparation method and leakage risk monitoring application thereof

Info

Publication number: CN120177465A
Application number: CN202510310772.3A
Authority: CN
Inventors: 张冬至; 毛钰菱; 张昊; 朱亮; 李国林; 曾景斌
Original assignee: China University of Petroleum East China
Current assignee: China University of Petroleum East China
Priority date: 2025-03-17
Filing date: 2025-03-17
Publication date: 2025-06-20

Abstract

The invention belongs to the technical field of production control, and particularly relates to a wearable/attachable ammonia colorimetric sensor, a preparation method and leakage risk monitoring application thereof. The invention discloses an attachable and stretchable ammonia colorimetric sensor which is deposited on a non-woven fabric through electro-spinning of polylactic acid (PLA) based on bromocresol green (BCG). The extraction of the feature color data is realized by combining a deep learning semantic segmentation algorithm, and the data is converted into CIE LaBcolor space so as to analyze and compare colors more accurately. The deep neural network is adopted to realize the conversion from color data to gas concentration, and the real-time monitoring function of the ammonia leakage is realized with low power consumption, and is wearable/attachable and visual.

Description

Wearable/attachable ammonia colorimetric sensor, preparation method and leakage risk monitoring application thereof

Technical Field

The invention belongs to the technical field of production control, and particularly relates to a wearable/attachable ammonia colorimetric sensor, a preparation method and leakage risk monitoring application thereof.

Background

With the development of the age, the industrialization process is vigorous, but a large amount of industrial toxic gases and chemicals are generated at the same time, the human health, the ecological system and the overall air quality are greatly influenced, and more attention is paid to the safety of the chemicals. Ammonia is a hazardous gas and also an important marker, and is commonly used and detected in the production of pharmaceuticals, polymers, food, fertilizers, explosives, cleaning products and textiles. Studies have shown that ammonia becomes flammable when the concentration of ammonia in air reaches 15-28%. Ammonia (< 1 ppm) can irritate eyes, throat and nose. When the concentration of gaseous ammonia reaches 25ppm, in addition to dangerous damage to the respiratory system, skin and eyes may be burned, whereas the tolerance limit of the human body is about 700ppm, and short-term exposure to environments above this concentration may lead to dyspnea and even death. The National Institute for Occupational Safety and Health (NIOSH) limited the allowable contact limit for NH ₃ to 25ppm. Therefore, there is an urgent need to develop a method with high sensitivity, accuracy and selectivity, which can simply and rapidly perform on-site real-time detection of NH ₃.

Various technologies have emerged for ammonia detection including semiconductor sensors, electrochemical sensors, liquid chromatography, gas chromatography, and optical sensors. Although these "conventional" gas sensors find widespread use in industry, they suffer from a number of disadvantages, including high energy consumption, high cost, unstable performance, and low detection range and response sensitivity. These limitations result in their poor mobility, stability and in most cases are not suitable for real-time monitoring and analysis in the field. In addition, these sensors often also require reliance on trained technicians for operation and maintenance.

Therefore, developing an early warning system capable of meeting the real-time monitoring requirement of industrial sites on gas has great significance in the technical fields of safe production and production control.

Disclosure of Invention

In view of this, in order to meet the requirements of industrial sites on real-time monitoring of gas, the invention develops a wearable/attachable ammonia colorimetric sensor based on the combination of a deep learning algorithm and an optical sensor, and a low-power-consumption and visual long-term real-time monitoring and early warning system for ammonia leakage and a use method thereof.

In order to achieve the above object, a first object of the present invention is to provide a method for preparing a wearable/attachable ammonia colorimetric sensor, which adopts the following technical scheme:

A preparation method of a wearable/attachable ammonia colorimetric sensor comprises the step of depositing polylactic acid of bromocresol green on non-woven fabrics in an electrostatic spinning manner to obtain the wearable/attachable ammonia colorimetric sensor.

It is worth noting that the optical sensor shows great application prospect in the field of NH ₃ detection based on the inherent advantages of the optical sensor, including real-time monitoring capability, high sensitivity and cost effectiveness. Colorimetric sensors belong to one class of optical sensors and are considered to be excellent products for the on-site real-time detection of NH ₃. Because the device has low power consumption, long-term stability, high selectivity, low detection limit and quick response, the most visual response can be provided, and the manpower consumption and the detection time are greatly reduced.

Compared with other colorimetric sensors, the bromocresol green adopted by the invention has higher sensitivity, and the NH ₃ colorimetric sensor with high sensitivity and high specific surface area can be manufactured in one step simply by blending the electrostatic spinning solution. Conventional sensor preparation methods generally require complex chemical reactions, post-treatments and multi-step operations, and the introduction of one-step electrospinning technology integrates all processes into one step, greatly simplifying the production process. Compared with the traditional sensor production method, the one-step electrostatic spinning disclosed by the invention can reduce the working procedures, simplify the operation, reduce the labor and time cost, reduce the dependence on expensive raw materials, and is beneficial to realizing large-scale production and commercial application.

Further, the preparation method of the wearable/attachable ammonia colorimetric sensor comprises the following specific steps:

(1) Preparing polylactic acid (PLA) solution by adopting a mixed solvent A, and then weighing a proper amount of bromocresol green (BCG) powder to dissolve in the polylactic acid solution to obtain an electrostatic spinning solution for later use;

(2) And sticking the non-woven fabric on a receiving plate of an electrostatic spinning machine, and spinning to obtain the wearable/attachable ammonia colorimetric sensor of the nanofiber film.

Further, in the step (1), the mixed solvent A is N, N-Dimethylformamide (DMF) and Tetrahydrofuran (THF) in a volume ratio of 1:1, the concentration of the polylactic acid solution is 6-10wt%, and the concentration of bromocresol green in the electrostatic spinning solution is 1-4wt%.

Further, in the step (2), the liquid feeding rate of the electrospinning was 0.06mm/min, the distance between the injector and the collecting device was set to 20cm, and the nanofibers were collected at negative voltage of-2 kV and positive voltage of 14kV, keeping the ambient humidity at 55%, and the temperature at 22 ℃.

It is worth to say that, compared with the existing NH ₃ sensor, the invention adopts a one-step electrostatic spinning technology, and the preparation process is simple. Based on the adhesion property, the sensor can be applied to monitoring in various complex environments, and the thin and flexible structure can be integrated into wearable equipment, so that a new solution is provided for personal safety and environmental monitoring, the simplified preparation process reduces the production cost, and the market competitiveness of the sensor is improved.

A second object of the present invention is to provide a wearable/attachable ammonia colorimetric sensor obtained by the above preparation method.

A wearable/attachable ammonia gas colorimetric sensor, the sensor comprising a gel, a fabric and nanofibers, with the gel attached on one side of the fabric and nanofibers attached on the other side.

It is worth noting that, the wearable/attachable ammonia colorimetric sensor disclosed by the invention has the main effects that the colloid is used as the first layer of the sensor from inside to outside according to the use form, and the colloid has the main function of providing good adhesiveness, so that the sensor can be firmly adhered to fabric or skin, and the sensor can be ensured to stably work for a long time and is not easy to fall off. This is particularly important for wearable or attachable sensors, especially in dynamic motion or use environments.

The middle fabric is the base layer in the sensor structure, giving the sensor good flexibility and wearability. The fabric provides a stable base structure for the entire sensor so that the colloid and nanofibers can be effectively held in a predetermined position. The fiber structure can enhance the durability and strength of the sensor and prevent deformation or damage under the action of external force.

The outermost nanofiber layer is a core functional part of the sensor and is responsible for detecting ammonia gas. Nanofibers have a very high specific surface area due to their unique microstructure. This means that more ammonia molecules can react with the sensor surface, thereby enhancing the sensitivity of the sensor to ammonia. The high specific surface area is particularly important for the detection of low concentration ammonia gas because it can significantly improve the gas adsorption efficiency, thereby lowering the minimum sensitivity threshold of the detection. The diameter of the nanofiber of the sensor disclosed by the invention ranges from 10 nm to 500nm, and an ideal network structure which is not too sparse and too dense is provided. Considering that too fine fibers may cause too weak materials to affect the durability of the sensor, while too coarse fibers may reduce the specific surface area and gas molecule contact efficiency to affect the sensitivity and response speed of the sensor. The nanofiber structure disclosed by the invention is beneficial to ensuring high sensitivity of the sensor and simultaneously keeping quick response and good stability.

Furthermore, the nanofiber is a bromocresol green/polylactic acid electrostatic spinning film, the nanofiber film is of a three-dimensional network structure and has a diameter of 10-500nm, and the fabric is a non-woven fabric medical breathable adhesive tape.

It is worth noting that the invention deposits bromocresol green (BCG)/polylactic acid (PLA) nanofiber membrane on a stretchable and adhered non-woven fabric through electrostatic spinning to form the wearable/attachable ammonia colorimetric sensor. The sensor is capable of visually observing a significant color change at 1ppm to 110ppm, the sensor changing from yellow to blue as the ammonia concentration increases. In addition, the sensor shows excellent tensile property and can be applied to various complex environments and stably used for more than 6 weeks.

The third object of the invention is to provide an ammonia leakage early warning system based on the wearable/attachable ammonia colorimetric sensor.

The utility model provides an ammonia leakage early warning system, includes wearable/can attach ammonia colorimetric sensor, camera picture module, sensor color information extraction module, gas concentration calculation module and gas concentration change line diagram module as described above, wherein, sensor color information extraction module and gas concentration calculation module have realized the monitoring of ammonia concentration through the real-time analysis to the image based on the degree of depth learning algorithm.

It is worth to say that the ammonia gas leakage early warning system disclosed by the invention combines a wearable/attachable ammonia gas colorimetric sensor, a camera picture module, a sensor color information extraction module, a gas concentration calculation module and a gas concentration change line diagram module, and realizes monitoring of ammonia gas concentration through a deep learning algorithm. The wearable/attachable ammonia colorimetric sensor technically improves the adhesive strength of colloid and ensures that the color change range has high sensitivity and response speed by controlling the diameter (10-500 nm) of the nanofiber, thereby increasing the flexible applicability of the system. The camera picture module adopts high resolution and high frame rate technology, has self-adaptive illumination function, and ensures effective capturing of color change in various light environments. The sensor color information extraction module realizes high-precision extraction and quick response of sensor color change through a precise color identification algorithm and a low-delay processing technology. The gas concentration calculation module performs high-precision fitting analysis through a deep learning algorithm and has a self-calibration mechanism so as to ensure the accuracy of concentration calculation. The gas concentration change line graph module can be updated in real time, and dynamic data is presented in a user-friendly interface mode, so that backtracking and statistical analysis of historical data are supported. The integration innovation of the system not only improves the intelligent level and response speed of ammonia monitoring, but also enhances the reliability of the system, is an important technical progress for improving the safety monitoring efficiency in various environments, and provides powerful data support for risk assessment and decision in practical application.

Thus, the ammonia colorimetric sensor is used to capture gas and convert a gas concentration signal to a color signal. The sensor realizes a wide NH ₃ detection range of 0-110ppm and can be reused. The camera picture module obtains sensor information under the shooting of an industrial camera, and ensures the definition of images under the resolution of 4K. The sensor color information extraction module accurately extracts the sensor color part from the complex environment based on DeepLabv3+ deep learning algorithm, and the accuracy rate is more than 98.4%, which is greatly improved compared with other algorithms. The gas concentration calculation module outputs a gas concentration value from the acquired CIE Lab and RGB color information based on a multi-layer perceptron (MLP) deep learning algorithm, so that the conversion from the color information to the gas concentration is realized, and the accuracy rate is more than 99.2%. The gas concentration change line diagram module is an intuitive visual tool, and helps a user to quickly know the rising, falling or stabilizing trend of the gas concentration through a clear line diagram mode, so that the dynamic change of the gas concentration value can be monitored in real time, and data update can be carried out according to a set fixed refreshing frequency, so that powerful support is provided for real-time monitoring and early warning.

Further, the wearable/attachable ammonia colorimetric sensor can be arranged on the surface of a human body wearable device terminal, an industrial production pipeline and a device or other objects exposed to the production environment.

The ammonia colorimetric sensor disclosed by the invention has good durability, excellent adhesiveness and tensile property, has a wide application prospect in the field of human body wearability, and can be conveniently adhered to the chest, arms and other parts of a human body for detecting ammonia. When a human body moves, such as an arm bends, the ammonia sensing patch can be firmly attached to clothes without affecting the detection function. Meanwhile, the stretchability and the adhesiveness of the ammonia colorimetric sensor are utilized to easily adhere to the surface of an object. Considering that ammonia leakage frequently occurs to key parts such as pipelines in chemical production, the ammonia colorimetric sensor can be arranged on the surfaces of industrial production pipelines and devices, so that the ammonia colorimetric sensor can not only provide quantitative information such as ammonia concentration, but also identify the position of ammonia leakage, thereby providing powerful technical support and theoretical basis for safety monitoring of chemical plants.

The fourth object of the invention is to provide an ammonia gas leakage early warning and monitoring method using the system.

An ammonia leakage early warning and monitoring method, which carries out ammonia leakage early warning and monitoring through the early warning system comprises the following steps:

Acquiring color data of an ammonia colorimetric sensor;

Extracting color information of a sensor from an environment image by adopting an image segmentation algorithm, converting the extracted picture information into RGB three channel values, and then converting the RGB three channel values into CIE Lab space to calculate a color difference (delta E) value;

According to a preset neural network model, calculating the concentration of the current NH ₃ based on the input RGB value and the delta E value;

And matching a corresponding preset early warning strategy according to the NH ₃ concentration information, and carrying out ammonia leakage monitoring early warning on the terminal according to the preset early warning strategy.

It is worth to be noted that, in order to realize real-time monitoring of NH ₃ concentration in the environment, first, an image segmentation algorithm is adopted to extract color information of the sensor from the environment image, so as to provide basic data for subsequent color analysis. Subsequently, the extracted picture information is converted into RGB three-channel values, and then converted into CIE Lab space to calculate a color difference (Δe) value, which is a key index for evaluating the NH ₃ concentration change. Based on the RGB values and ΔE values, input into a pre-trained neural network model that is capable of calculating the current NH ₃ concentration.

Acquiring sensor color data prior to gas concentration detection is a critical step, and this involves extracting feature data from the image. According to the invention, after the sensor color change process is trained by adopting the semantic segmentation DeeplabV & lt3+ & gt model, information extraction can be performed on the sensor in different NH ₃ concentration environments, and DeeplabV & lt3+ & gt can keep good extraction performance under different illumination conditions, so that the accuracy of concentration detection can be improved.

The ammonia concentration detection model based on the multilayer feedforward neural network (MLP) remarkably improves the detection precision under the introduction of a deep learning technology, and shows stronger generalization capability and stability. The model optimizes the weight and the deviation in the network through a back propagation algorithm, and minimizes a Mean Square Error (MSE) loss function on a training set by means of a gradient descent method, so that accurate modeling and prediction of ammonia concentration are realized. In a specific design, the model uses RGB color values and delta E color difference values as input features of the neural network, and the inputs capture the mapping relation between the data features and the NH ₃ concentration after nonlinear transformation of the hidden layer. In the training stage, network parameters are continuously and iteratively adjusted, so that the model can effectively fit a complex nonlinear relation between the gas concentration and the input characteristics. The method not only fully plays the advantages of deep learning in aspects of feature extraction and pattern recognition, but also provides an effective solution for high-precision ammonia concentration detection in practical application.

In order to enhance the generalization capability of the model and effectively reduce the overfitting risk, a Dropout technique is introduced as a regularization means. In the present invention, dropout uses the probability value p (i.e., the drop rate) generated by the bernoulli distribution during the training phase to randomly remove some neurons in the neural network to achieve an effect similar to model integration. In addition, dropout layers alternate between hidden and output layers of the network to further improve the robustness of the model.

Furthermore, the ammonia gas leakage early warning and monitoring method further comprises the step of ensuring timeliness of concentration data through preset sampling frequency.

It should be noted that DeepLabV3+ is a deep learning model based on Convolutional Neural Network (CNN), focusing on the semantic segmentation of images. The method extracts high-resolution spatial features through hole convolution (Dilated Convolution) and an encoding-decoding structure (Encoder-Decoder), and is particularly suitable for image segmentation tasks in complex environments. MLP (multi-layer perceptron) is a classical neural network architecture, commonly used to process tabular data or simple image classification tasks. The MLP processes the input data through multiple fully connected layers (Fully Connected Layers), generates a nonlinear map at each layer through an activation function, and finally outputs the prediction result. The preset neural network model can be used for reasoning through trained parameters (weights and biases) under new input data (such as new environment images or sensor data) to generate output. The process does not need retraining, only data needs to be input, and the model can output results. By combining image segmentation, color feature extraction and concentration prediction, the preset early warning strategy can timely send out early warning signals when the environment changes. For example, when the ammonia concentration exceeds a preset threshold, the system may automatically activate an alarm mechanism to take emergency action in advance. Therefore, the ammonia gas leakage early warning system and the ammonia gas leakage early warning method can monitor the concentration of the ammonia gas in real time, the sampling frequency can be manually fixed to ensure the timeliness of concentration data, and when the sampling frequency exceeds a set safety threshold, the system automatically triggers an alarm and carries out early warning in modes of window reminding, information sending and the like.

Compared with the prior art, the invention discloses a high-sensitivity stretchable and adhesive ammonia colorimetric sensor and an ammonia leakage early warning system for real-time monitoring, which are used for quantitative ammonia detection and early warning of ammonia leakage. In the presence of NH ₃, the color of the ammonia colorimetric sensor changes from yellow to blue due to the deprotonation of the BCG dye on the nanofibers, which again restores the original color for repeated use. The RGB value of the color image is extracted and the delta E response value is calculated, so that quantitative analysis and precision improvement are facilitated. In addition, because the stretchability and the adhesiveness of the ammonia gas leakage monitoring device enable flexible placement, the ammonia gas leakage monitoring device is suitable for real-time monitoring of ammonia gas leakage in various complex environments of chemical places. The ammonia colorimetric sensor is suitable for the technical field of production control and provides higher sensitivity and unique color change. In addition, the sensing system has the potential of home and office air quality monitoring, and is particularly suitable for places with low NH ₃ concentration and possibly threatening health. The sensing system is combined with intelligent equipment, so that data real-time transmission and analysis are realized, and a user can grasp the dynamic change of the ammonia concentration at any time. The system not only has high-efficiency NH ₃ detection capability, but also has intelligence, convenience and economy, and provides a convenient and efficient solution for field application.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic illustration of the preparation flow of colorimetric sensors of example 1 and comparative example 1 of the present invention.

Fig. 2 shows the surface morphology and the structure cross-sectional morphology of the four colorimetric sensors in experimental example 1 of the present invention.

Fig. 3 is a schematic diagram of an ammonia gas leakage early warning system and an algorithm flow chart in embodiment 2 of the present invention.

Fig. 4 is a schematic diagram of a practical simulation application in embodiment 3 of the present invention.

Fig. 5 is a physical diagram of color change and Δe response values of four colorimetric sensors in experimental example 2 of the present invention.

FIG. 6 is a graph showing the degree of change, ΔE response curve, and linear fitting of ΔE to gas concentration of the ammonia colorimetric sensor in the range of 0 to 140ppmNH ₃ in experimental example 2 of the present invention.

FIG. 7 shows the results of the anti-interference performance and stability of the ammonia colorimetric sensor according to example 3 of the present invention.

Fig. 8 is a tensile test result and a wearable application example of the ammonia colorimetric sensor in experimental example 4 of the present invention.

Detailed Description

The following description of the technical solutions in the embodiments of the present invention will be clear and complete, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The word "embodiment" as used herein does not necessarily mean that any embodiment described as "exemplary" is preferred or advantageous over other embodiments. Performance index testing in the examples of the present application, unless otherwise specified, was performed using conventional testing methods in the art. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure.

Unless otherwise defined, technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs, and other test methods and techniques not specifically mentioned herein are meant to be common to those of ordinary skill in the art.

Numerous specific details are set forth in the following examples in order to provide a better understanding of the present application. It will be understood by those skilled in the art that the present application may be practiced without some of these specific details. In the examples, some methods, means, instruments, devices, etc. well known to those skilled in the art are not described in detail in order to highlight the gist of the present application.

On the premise of no conflict, the technical features disclosed by the embodiment of the application can be combined at will, and the obtained technical scheme belongs to the disclosure of the embodiment of the application.

The invention discloses a wearable/attachable ammonia colorimetric sensor, a preparation method and leakage risk monitoring application thereof, and belongs to the technical field of production control. The invention discloses an attachable and stretchable ammonia colorimetric sensor which is deposited on a non-woven fabric through electro-spinning of polylactic acid (PLA) based on bromocresol green (BCG). The extraction of the feature color data is realized by combining a deep learning semantic segmentation algorithm, and the data is converted into CIE LaBcolor space so as to analyze and compare colors more accurately. The deep neural network is adopted to realize the conversion from color data to gas concentration, and the real-time monitoring function of the ammonia leakage is realized with low power consumption, and is wearable/attachable and visual.

The present invention will be further specifically illustrated by the following examples, which are not to be construed as limiting the invention, but rather as falling within the scope of the present invention, for some non-essential modifications and adaptations of the invention that are apparent to those skilled in the art based on the foregoing disclosure.

The invention relates to an experimental material:

Bromocresol green (BCG, indicator grade), polylactic acid (PLA, mw-60,000), N, N-dimethylformamide (DMF, AR grade), tetrahydrofuran (THF, ACS grade), absolute ethanol (C ₂H₆ O9, > 99.5%), available from Shanghai Ala Biochemical technologies Co., ltd. Nonwoven fabric, filter paper, meltblown cloth were purchased from Zhejiang gold three-part company, inc.

Example 1

First, DMF and THF 4.8mL (DMF: thf=1:1) were added in a 50mL beaker, 8wt% PLA powder was weighed into the beaker slowly and stirred at room temperature for 5 hours until the PLA powder was completely dissolved. 2wt% of BCG powder was weighed into a beaker slowly and stirred at room temperature for 1 hour until the BCG powder was completely dissolved. Standing for 30 minutes at room temperature to prepare the electrostatic spinning solution. The resulting electrospinning solution was sucked into a disposable syringe and electrospun with a 20 gauge metal needle. The electrostatic spinning equipment consists of an injection system, a collecting device and a high-voltage power supply. The liquid feeding rate was set to 0.06mm/min, the distance between the syringe and the collecting device was set to 20cm, and nanofibers were collected at negative voltage of-2 kV and positive voltage of 14kV, keeping the ambient humidity at 55%, and the temperature at 22 ℃. The nonwoven fabric was stuck to a receiving plate of an electrostatic spinning machine, and after spinning for 5 hours, a colorimetric sensor of a 0.6mm nanofiber film was obtained, as shown in fig. 1 (a).

Example 2

An ammonia leakage early warning system comprises an ammonia colorimetric sensor, a camera picture module, a sensor color information extraction module, a gas concentration calculation module and a gas concentration change line drawing module. In the embodiment, a rogue c1000s camera is adopted, and a color analysis algorithm is combined to extract and analyze RGB characteristic information of a sensor sensing area (10 mm multiplied by 10 mm) in real time, detect the current concentration of NH ₃ gas and display the detected concentration in an intelligent terminal. The sensor is kept at a distance of 10cm from the camera to ensure the sharpness of the image and the accuracy of the color, as shown in fig. 3 (a).

When the ammonia gas leakage monitoring and early warning method is used, color data of an ammonia gas colorimetric sensor are firstly obtained, then color information of the sensor is extracted from an environment image by adopting an image segmentation algorithm, the extracted image information is converted into RGB three-channel values, the RGB three-channel values are converted into CIE Lab space to calculate a color difference delta E value, then the concentration of the current NH ₃ is calculated based on the input RGB values and delta E values according to a preset neural network model, finally a corresponding preset early warning strategy is matched according to the NH ₃ concentration information, and ammonia gas leakage monitoring and early warning is carried out at a terminal according to the preset early warning strategy.

As the NH ₃ concentration increased, the color of the sensor surface changed from yellow to blue. In order to simplify the image analysis process, the invention applies a CIE DE2000 color difference calculation formula based on CIE L a b. Converting the RGB color space into an XYZ color space, calculating according to the formula (1), and then converting the XYZ color space into an Lab color space, so as to obtain an Lab value expression of all image colors, and calculating according to the formulas (2) and (3). And finally, calling a function of the CIE DE2000 color difference calculation formula to obtain color difference (delta E). ΔE is defined as the color response of the colorimetric sensor, and changes in ΔE value are directly related to changes in NH ₃ concentration, thereby providing a quantitative method for detection of NH ₃.

In order to realize the real-time monitoring of the gas concentration change in the gas chamber, a colorimetric sensing system monitoring interface is developed based on a Qt platform. The interface can continuously call algorithm analysis, and display the change of the gas concentration in real time in the form of a line graph, and through the real-time monitoring, the change of the ammonia concentration can be effectively detected, and data support is provided for subsequent optimization and application.

When the color sensor is used, the color information of the sensor is firstly extracted from the environment image by adopting an image segmentation algorithm, so that basic data is provided for subsequent color analysis. Subsequently, the extracted picture information is converted into RGB three-channel values, and then converted into CIE Lab space to calculate a color difference (Δe) value, which is a key index for evaluating the NH ₃ concentration change. Based on the RGB values and ΔE values, input into a pre-trained neural network model that is capable of calculating the current NH ₃ concentration. As shown in fig. 3 (b), the photo algorithm flow chart realizes the detection of the gas concentration.

The neural network model trains data through DeepLabv & lt3+ & gt semantic segmentation algorithm and multi-layer perceptron (MLP) architecture and generates a model, deepLabv & lt3+ & gt is a semantic segmentation algorithm based on a Convolutional Neural Network (CNN), and the core innovation is how to improve the precision and efficiency of image segmentation. The algorithm effectively processes high resolution information in an image by introducing hole convolution (Dilated Convolution) and encoder-decoder structure and expands its receptive field (RECEPTIVE FIELD), thereby capturing a wider range of context information, deepLabv3+ uses Xception convolutional neural network structure (depth separable convolution) in the encoder section to reduce the computational and parameter amounts while maintaining efficient feature extraction capability. The decoder part is used for recovering the high-dimensional semantic features extracted by the encoder to higher resolution, so that the details and the accuracy of image segmentation are improved. Through the encoder-decoder structure, deepLabv3+ can effectively carry out fine segmentation on images in a complex scene, and the optical sensor can be accurately extracted from the complex background. A multilayer perceptron (MLP) is a classical feed-forward neural network structure consisting of an input layer, multiple hidden layers and an output layer. Each layer of MLP is information-transferred through connections between neurons, and the neurons of each layer are non-linearly transformed by an activation function. MLP exhibits a strong capability in processing high-dimensional data and nonlinear relationships, and is particularly useful for classification tasks and modeling of complex features. Therefore, the gas concentration output model is constructed by using the method, and the current gas concentration value is predicted by comparing the color information in the neural network.

The preset early warning strategy is to analyze by utilizing DeepLabv & lt3+ & gt model in combination with an optical sensor in the detection of the concentration of the environmental gas. First, an optical sensor captures an image of the environment, capturing the interaction of the gas with the optical signal. Subsequently, the DeepLabv3+ model semantically segments the image, precisely separating the sensor region from the complex background. Color values are then extracted from the segmented gas regions and converted from the RGB color space to the CIE Lab color space, which is more closely related to human visual perception and which more accurately describes color changes. Finally, the converted CIE Lab color values and RGB values are input into a multi-layer perceptron (MLP) model for analysis and prediction. The MLP can rapidly and accurately output the gas concentration in the current environment by learning the complex nonlinear relation between the color value and the gas concentration. The method combines the image segmentation capability of deep learning and the prediction capability of machine learning, has the advantages of non-contact detection, high flexibility, strong adaptability and the like, is particularly suitable for multi-gas detection in complex environments, and has wide application prospect.

Example 3

Ammonia gas leakage early warning system and practical application of detection method thereof:

As shown in fig. 4 (a), after gas leakage occurs in an industrial place, the color of the ammonia sensing patch changes, the camera transmits color information of the ammonia sensing patch in real time, the concentration is detected and displayed through algorithm processing performed on a PC end, and meanwhile, concentration data is uploaded through cloud service so as to achieve a remote monitoring function through a mobile phone App. The monitoring data during the experiment will be displayed in real time in the software and transmitted to the App and a red warning sign will be displayed immediately after the threshold concentration is exceeded.

A section of PVC pipeline which is being introduced with NH ₃ is selected as an experimental object, and an oval hole is accurately manufactured on the PVC pipeline so as to simulate the pipeline damage possibly occurring in actual production. In the experiment, as shown in fig. 4 (b), an ammonia sensing patch was disposed near the hole, which was easily attached to the surface of the pipe by virtue of its stretchability and adhesiveness. When NH ₃ flows through the pipe, ammonia leaks from the holes, the ammonia sensing patch quickly turns blue, and the leakage direction can be clearly seen in the changing process. The ammonia concentration detection can be performed by identifying the current color through a colorimetric system. Experimental results show that the ammonia sensing patch not only can provide quantitative information such as ammonia concentration and the like, but also can identify the position of ammonia leakage, thereby providing powerful technical support and theoretical basis for safety monitoring of chemical plants.

In order to further demonstrate the beneficial effects of the present invention to better understand the present invention, the ammonia gas colorimetric sensor and the preparation method thereof, the ammonia gas leakage early warning system and the monitoring method using the same disclosed herein are further illustrated by the following comparative examples and experimental examples, but the present invention is not to be construed as limited by the following, and the method properties obtained by other measurement experiments performed by those skilled in the art according to the above-described summary of the present invention and the application according to the above-described properties are also considered to be within the scope of the present invention.

Comparative example 1

First, 20mL of absolute ethanol was added to a 50mL beaker, 40mg of BCG powder was weighed, slowly added to the beaker, and stirred at room temperature for 15 minutes until complete dissolution was achieved to form BCG solution. Then, a portion of each of 10mm x 10mm meltblown, nonwoven fabric, and filter paper was cut, and 5. Mu.L of BCG solution was sucked by a pipette and applied onto the surfaces of the meltblown, nonwoven fabric, and filter paper. Finally, three wetted sensors were dried at 60 ℃ for 3 minutes and then removed to form a colorimetric sensor, as shown in fig. 1 (b).

Experimental example 1

The four colorimetric sensors prepared in comparative example 1 and comparative example 1 were used to characterize the surface morphology and the structural cross-sectional morphology of the nanofiber membrane by scanning electron microscopy (SEM, hitachi S-4800, japan).

Fig. 2 (a) shows the surface, cross-section and sample images of BCG/PLA electrospun films. The images show that the addition of BCG does not significantly affect the uniformity and diameter of the fiber, but gives the fiber surface more roughness, which may be related to the distribution of BCG on the fiber surface. In addition, no obvious agglomeration or caking phenomenon was observed on the fiber surface, indicating good dispersibility of BCG in polylactic acid. From SEM images of the bonding cross section between BCG/PLA electrospun film and nonwoven, it can be observed that a good bonding interface is formed between the fibers without significant voids or separation. The smooth and uniform surface of the fiber shows affinity between polylactic acid and nonwoven fabric, probably due to the addition of bromocresol green to enhance the compatibility of the composite film. In particular, the structure of the contact area of the fibers with the nonwoven exhibits continuity and consistency, indicating good mechanical adhesion between them. The tightly attached structure enhances the stability and durability between the film and the non-woven fabric, and improves the overall performance of the film in practical application. Fig. 2 (b) shows SEM characterization images and sample images of the meltblown. On the surface of the melt-blown base material, BCG is uniformly distributed on the surface of the fiber to form small particles or a film layer, and the small particles or the film layer is covered on the surface of the fiber, so that no obvious aggregation phenomenon exists, and good coating uniformity is shown. Fig. 2 (c) shows SEM characterization images of the nonwoven substrate and sample images. On nonwoven substrates, BCG is more dispersed and sometimes localized aggregation occurs, especially in the cross-over areas of fiber interweaving, possibly due to the presence of more micropores and irregularities on the nonwoven surface, resulting in BCG being more prone to aggregation and thicker coatings at these places. Fig. 2 (d) shows SEM characterization images of the filter paper substrate and a sample plot. On filter paper substrates, most of the BCG adheres to fiber intersections or surfaces, forming a coarser coating, and some areas of the particles may be larger, forming small clumps of structure, with surfaces that are less smooth than the meltblown fabric substrate.

Experimental example 2

The ammonia response characteristics of the NH ₃ sensors of the four different substrates are compared, namely an electrostatic spinning film ammonia sensor, a melt-blown cloth, a non-woven fabric and a filter paper substrate ammonia sensor. These sensors were all tested under controlled environmental conditions, i.e. a relative humidity of 65±2% and a temperature of 26 ℃. During the test, the response characteristics at different NH ₃ concentrations were simulated by injecting NH ₃ at a concentration from 0ppm to 100ppm into the chamber.

The results indicate that the electrospun thin film ammonia sensor exhibits a more uniform color change upon exposure to ammonia (fig. 5 a), which provides a more accurate basis for subsequent color data extraction and concentration detection. Through quantitative analysis of Δe, the electrospun films showed excellent linearity and a wider detection range over the concentration range of 0-100ppm NH ₃, as shown in fig. 5 (b). Therefore, the color change uniformity, the linearity and the detection range of the electrostatic spinning film ammonia sensor are better, the high sensitivity and the good selectivity are realized in the detection of the concentration of NH ₃, and the method has important significance for the detection of NH ₃ in the fields of environmental monitoring and industrial safety.

Further, under the same conditions, the color response of the ammonia colorimetric sensor of the present invention was tested for NH ₃ concentrations from 0-140ppm, with the ammonia sensor patch exhibiting a distinct color change from yellow to blue (fig. 6 b). The color difference can hardly be seen when the color change picture of the ammonia sensing patch at the concentration of 0-140ppm is converted into delta E value (figure 6 c), the color difference can be seen when delta E is less than 1.0, the color difference can be seen when the color change picture is carefully observed when delta E1-2, the color difference can be seen when delta E2-10, and the color is different when delta E > 10. After being captured by the camera of the system, the ammonia sensing patch can be seen to have a color change at a concentration of 1ppm, and the delta E value is greater than 1.5. The maximum response limit of the sensing patch is about 110ppm through testing, and the color is unchanged after NH ₃ is added continuously. And the delta E response value at the concentration of 0-110ppm is subjected to linear fitting (figure 6 d), so that the ammonia sensing patch has better linearity, and the current NH ₃ concentration value is better identified.

Experimental example 3

The ammonia colorimetric sensor disclosed by the invention is tested for anti-interference performance and stability.

FIG. 7 (a) shows good selectivity when 10ppm NH ₃ and 10ppm NO ₂、O₂、SO₂、CH₄、H₂、C₄H₁₀、CO、H₂ S, respectively, are present in the chamber at the same time, and the ΔE is observed to remain at a response value that normally only contains 10ppmNH ₃. Fig. 7 (b) shows that no significant color change occurred after 10ppmNO ₂、O₂、SO₂、CH₄、H₂、C₄H₁₀、CO、H₂ S was injected into the air chamber in sequence, and the color was changed immediately after 10ppmNH ₃ was injected, further verifying the selectivity.

The long-term use of the sensor was important for real-time monitoring during industrial leaks, so the stability of the ammonia sensing patch was tested over 6 weeks (fig. 7 c), 10ppm NH ₃ was injected each time, and the Δe response value was not significantly different, so it was demonstrated to have long-term stability. The ammonia sensing patch was tested for recovery speed at 60 ℃ and 30 ℃ based on the protonation reaction so that the initial color could be recovered, as shown in fig. 7 (d), the ammonia sensing patch recovered faster at 60 ℃ and within 20 minutes, and recovered naturally slower at 30 ℃. Based on the recovery characteristics of the ammonia sensing patch, the sensor was tested three times in succession for color change at 10ppm (fig. 7E), Δe remained consistent, so it was verified that it could be reused multiple times. The ammonia sensing patch has extremely fast response to NH ₃, the dynamic change curves (figure 7 f) of the ammonia sensing patch with NH ₃ concentration at 20, 40, 60, 80 and 100ppm respectively are tested, the ammonia sensing patch can be observed to be in a stable state at 15s basically at different concentrations, and the leakage of ammonia gas in chemical places is detected more quickly and obviously. The invention tests the color change effect on the ammonia sensing sticking cloth at different normal temperatures, and tests the color change reaction by injecting 10ppm ammonia gas into the air chamber at the temperature of 20-35 ℃, wherein delta E is still kept at the same level, as shown in figure 7 (g), so that the color change degree of the sensor at the same concentration NH ₃ is not influenced at different normal temperatures. The invention explores the color change effect of humidity on ammonia sensing patch, and experimental results show that under high humidity environment, the same concentration of NH ₃ can cause larger delta E response change (figure 7 h) and more remarkable color change (figure 7 i). this phenomenon can be attributed to the deprotonation process in the reaction of BCG with ammonia, wherein water molecules act as proton transport medium, facilitating proton transfer. Specifically, when water molecules are absorbed into the mat, they promote a reaction between NH ₃ and H ₂ O, producing NH ⁴⁺ and OH ^-, thereby creating an alkaline environment at the film surface. Thus, under high RH conditions, the formation amounts of NH ⁴⁺ and OH ^- on the film surface increased, resulting in more pronounced color change.

Experimental example 4

To evaluate the tensile properties of the ammonia colorimetric sensor patch, a tensile test was performed. These tests were carried out on tensile testing machines (TM 2101-T5) at a test speed of 10mm/min and a temperature of 22℃and with an ammonia colorimetric sensor of 50mm by 15mm as the test object.

As shown in fig. 8 (a), the strong extensibility of the ammonia sensing patch was tested, the BCG/PLA electrospun film was uniformly distributed on the surface, and no obvious breakage and tearing of the film occurred during the stretching process. The sensor was subjected to continuous 50-cycle stretching for 17mm, and as shown in fig. 8 (b), the sensor surface was slightly wrinkled and stretched in length, but the surface was still free from breakage and tearing, and durability was confirmed. Through testing, the maximum tensile strength of the ammonia sensing patch can reach 43.12kPa (figure 8 c) when the ammonia sensing patch breaks, and the loading/unloading curve of 50 continuous cycles under tensile strain can be seen, the tensile stress and the dissipation energy are sequentially reduced (figure 8 d), and the curve of the loading/unloading process is basically consistent with the increase of the cycle times. In addition, a significant hysteresis loop is observed in the first cycle, mainly because the fibers of the nonwoven are randomly arranged, and during stretching, mutual slippage and rearrangement between the fibers can occur. Such slippage and rearrangement can consume a portion of the applied energy and cannot be fully recovered upon unloading, resulting in the formation of hysteresis loops. In the subsequent load/unload curves, the hysteresis loop was limited, indicating excellent elasticity of the ammonia sensing patch.

The ammonia sensing patch has wide application prospect in the field of human body wearable due to excellent adhesiveness and tensile property. As shown in fig. 8 (e), the patch can be conveniently attached to the chest, arm, etc. of a human body for detecting ammonia gas. When a human body moves, such as an arm is bent, the ammonia sensing patch can be firmly attached to clothes without affecting the detection function, and the ammonia sensing patch is free to stretch in the natural motion range of the human body due to the excellent mechanical property and adhesion property, cannot be damaged or lose functions due to stretching, has huge application potential in the wearable field of the human body, and can provide effective technical support for health monitoring and environmental safety.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A preparation method of a wearable/attachable ammonia colorimetric sensor is characterized in that bromocresol green polylactic acid is subjected to electrostatic spinning and deposited on non-woven fabrics, and the wearable/attachable ammonia colorimetric sensor is obtained.

2. The preparation method according to claim 1, wherein the specific steps include:

(1) Preparing a polylactic acid solution by adopting a mixed solvent A, and then weighing a proper amount of bromocresol green powder to dissolve in the polylactic acid solution to obtain an electrostatic spinning solution for later use;

3. The method according to claim 2, wherein in the step (1), the mixed solvent a is N, N-dimethylformamide and tetrahydrofuran in a volume ratio of 1:1, the concentration of the polylactic acid solution is 6wt% to 10wt%, and the concentration of bromocresol green in the electrospinning solution is 1wt% to 4wt%.

4. The method according to claim 2, wherein in the step (2), the liquid feeding rate of the electrospinning is 0.06mm/min, the distance between the injector and the collecting device is set to 20cm, and the nanofibers are collected at a negative voltage of-2 kV and a positive voltage of 14kV, and the ambient humidity is maintained at 55% and the temperature is 22 ℃.

5. The wearable/attachable ammonia gas colorimetric sensor prepared by the method according to any one of claims 1 to 4, wherein the sensor comprises a colloid, a fabric and nanofibers, wherein the colloid is attached to one side of the fabric, and the nanofibers are attached to the other side of the fabric.

6. The wearable/attachable ammonia colorimetric sensor according to claim 5, wherein the nanofiber is a bromocresol green/polylactic acid electrospun film, the nanofiber film is of a three-dimensional network structure and has a diameter of 10-500nm, and the fabric is a non-woven medical breathable tape.

7. An ammonia leakage early warning system is characterized by comprising the wearable/attachable ammonia colorimetric sensor, a camera picture module, a sensor color information extraction module, a gas concentration calculation module and a gas concentration change line diagram module according to any one of claims 5-6, wherein the sensor color information extraction module and the gas concentration calculation module realize ammonia concentration monitoring through real-time analysis of images based on a deep learning algorithm.

8. The ammonia gas leakage pre-warning system of claim 7, wherein the wearable/attachable ammonia gas colorimetric sensor is capable of being disposed on a human body wearable device terminal, an industrial production pipeline and device surface, or other surfaces of objects exposed to a production environment.

9. An ammonia gas leakage early warning and monitoring method, characterized in that the ammonia gas leakage early warning and monitoring method is carried out through an early warning system according to any one of claims 7-8, and the method comprises the following steps:

Acquiring color data of an ammonia colorimetric sensor;

Extracting color information of a sensor from an environment image by adopting an image segmentation algorithm, converting the extracted picture information into RGB three channel values, and then converting the RGB three channel values into CIE Lab space to calculate a color difference delta E value;

10. The ammonia gas leak early warning and monitoring method of claim 9, further comprising ensuring timeliness of the concentration data by presetting a sampling frequency.